Underwater vehicle path planning using a multi-beam forward looking sonar

Describes an obstacle avoidance and path planning system for underwater vehicles based on a multi-beam forward looking sonar sensor. The real-time data flow (acoustic images) at the input of the system is first processed (segmentation and feature extraction) to create a representation of the workspace of the vehicle. This representation uses constructive solid geometry (CSG) to create a convex set of obstacles defining the workspace. We also take advantage of the real-time data stream to track the obstacles in the subsequent frames to obtain their dynamic characteristics. This will also allow us to optimise the preprocessing phases in segmenting only the relevant part of the images as well as to take into account obstacles which are no longer in the field of view of the sonar in the path planning phase. A well proven nonlinear search (sequential quadratic programming) is then employed, where obstacles are expressed as constraints in the search space. This approach is less affected by local minima than classical methods using potential fields. The proposed system is not only capable of obstacle avoidance but also of path planning in complex environments which include fast moving obstacles. Preliminary results obtained on real data are shown and discussed.